© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89348
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingu
    -0.28
    ŀ
    -0.28
    åłķ
    -0.26
    yme
    -0.26
    ymes
    -0.25
     dụ
    -0.25
     marginal
    -0.25
    mix
    -0.24
    _activities
    -0.24
    living
    -0.24
    POSITIVE LOGITS
    velt
    0.27
    棵æłij
    0.25
     Era
    0.25
     kiá»ĩn
    0.25
    eker
    0.25
     vad
    0.24
    人æ°ijæ³ķéĻ¢
    0.24
     sampled
    0.24
    åīįæıIJæĺ¯
    0.24
    .extra
    0.24
    Activations Density 1.287%

    No Known Activations

    This feature has no known activations.